© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1357
    Prev
    Next
    INDEX
    Explanations

    any thing

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     some
    -0.27
    estroy
    -0.23
     each
    -0.23
    oppable
    -0.22
    Dragging
    -0.22
    privation
    -0.22
    annies
    -0.22
    ,:),
    -0.21
     many
    -0.21
    buat
    -0.21
    POSITIVE LOGITS
    thing
    0.33
    THING
    0.33
     whatsoever
    0.32
    thin
    0.32
    /all
    0.28
    ht
    0.28
    things
    0.27
    berapa
    0.25
    place
    0.24
    ones
    0.24
    Activations Density 1.001%

    No Known Activations